Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to "Star" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "Star" followed by other words/franchises

    np_acts-logits-general · gemini-2.0-flash

    star followed by wars or trek

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    //
    -0.72
     Obrador
    -0.72
     дописавши
    -0.67
    }))
    -0.66
    (!__
    -0.65
    ]")]
    -0.64
    enic
    -0.64
    adaptiveStyles
    -0.64
    хьтан
    -0.63
    msgTypes
    -0.61
    POSITIVE LOGITS
     Star
    1.02
     STAR
    0.95
     Stars
    0.89
     star
    0.86
    Star
    0.85
     stars
    0.82
    STAR
    0.81
    Stars
    0.79
    star
    0.75
     Wars
    0.75
    Act Density 0.075%

    No Known Activations